
# importing all the necessary packages and set plots to be embedded inline.
import numpy as np
import pandas as pd
import matplotlib.pyplot as plt
import seaborn as sb
import calendar
import plotly.express as px
import time
%matplotlib inline


# Loading the Ford Gobike dataset 
bike_df=pd.read_csv('201902-fordgobike-tripdata.csv')

# displaying the first 5 rows of the Ford GoBike dataset.
bike_df.head(5)


# displaying the shape of the dataset
print(bike_df.shape)

(183412, 16)


# checking the datatypes of the dataset
print(bike_df.dtypes)

duration_sec                 int64
start_time                  object
end_time                    object
start_station_id           float64
start_station_name          object
start_station_latitude     float64
start_station_longitude    float64
end_station_id             float64
end_station_name            object
end_station_latitude       float64
end_station_longitude      float64
bike_id                      int64
user_type                   object
member_birth_year          float64
member_gender               object
bike_share_for_all_trip     object
dtype: object


# checking some general information about the dataset.
bike_df.info()

<class 'pandas.core.frame.DataFrame'>
RangeIndex: 183412 entries, 0 to 183411
Data columns (total 16 columns):
 #   Column                   Non-Null Count   Dtype  
---  ------                   --------------   -----  
 0   duration_sec             183412 non-null  int64  
 1   start_time               183412 non-null  object 
 2   end_time                 183412 non-null  object 
 3   start_station_id         183215 non-null  float64
 4   start_station_name       183215 non-null  object 
 5   start_station_latitude   183412 non-null  float64
 6   start_station_longitude  183412 non-null  float64
 7   end_station_id           183215 non-null  float64
 8   end_station_name         183215 non-null  object 
 9   end_station_latitude     183412 non-null  float64
 10  end_station_longitude    183412 non-null  float64
 11  bike_id                  183412 non-null  int64  
 12  user_type                183412 non-null  object 
 13  member_birth_year        175147 non-null  float64
 14  member_gender            175147 non-null  object 
 15  bike_share_for_all_trip  183412 non-null  object 
dtypes: float64(7), int64(2), object(7)
memory usage: 22.4+ MB


# checking the features/columns with missing values.
bike_df.isna().sum()

duration_sec                  0
start_time                    0
end_time                      0
start_station_id            197
start_station_name          197
start_station_latitude        0
start_station_longitude       0
end_station_id              197
end_station_name            197
end_station_latitude          0
end_station_longitude         0
bike_id                       0
user_type                     0
member_birth_year          8265
member_gender              8265
bike_share_for_all_trip       0
dtype: int64


# inputing missing values with "0" for missing numerical variables
missval_col=['start_station_id','end_station_id','member_birth_year']

for i in missval_col:
    bike_df[i]=bike_df[i].fillna(bike_df[i].mode()[0])


# inputing missing values with "None" for missing object type of variables.
bike_df['start_station_name'].fillna("None",inplace=True)
bike_df['end_station_name'].fillna("None",inplace=True)


# For the member_gender column, We will fill the null values with "No Gender"

bike_df['member_gender'].fillna("No Gender",inplace=True)


# Checking if the missing values have been inputed.
bike_df.isna().sum()

duration_sec               0
start_time                 0
end_time                   0
start_station_id           0
start_station_name         0
start_station_latitude     0
start_station_longitude    0
end_station_id             0
end_station_name           0
end_station_latitude       0
end_station_longitude      0
bike_id                    0
user_type                  0
member_birth_year          0
member_gender              0
bike_share_for_all_trip    0
dtype: int64


# Checking the descriptive statistics of the data.
bike_df.describe()


# changing the datatypes of certain selected features of interest to appropriate data types.

bike_df[['start_station_id','end_station_id','bike_id']]= bike_df[['start_station_id','end_station_id','bike_id']].astype('object')
bike_df[['user_type','member_gender']]= bike_df[['user_type','member_gender']].astype('category')
bike_df['member_birth_year']= bike_df['member_birth_year'].astype('int64')


# checking the unique values for member gender.
bike_df['member_gender'].unique()

['Male', 'No Gender', 'Other', 'Female']
Categories (4, object): ['Female', 'Male', 'No Gender', 'Other']


# Convert start time to morning, afternoon, and night of day
bike_df['start_time']=pd.to_datetime(bike_df['start_time'])
bike_df['start_hour']=bike_df['start_time'].apply(lambda i : i.hour)
bike_df['period_ofday']='morning'
bike_df['period_ofday'][(bike_df['start_hour'] >=12) & (bike_df['start_hour'] <=17)] = 'afternoon'
bike_df['period_ofday'][(bike_df['start_hour'] >=18) & (bike_df['start_hour'] <=23)] = 'night'

C:\Users\USER\AppData\Local\Temp\ipykernel_2580\1840100055.py:5: SettingWithCopyWarning: 
A value is trying to be set on a copy of a slice from a DataFrame

See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy
  bike_df['period_ofday'][(bike_df['start_hour'] >=12) & (bike_df['start_hour'] <=17)] = 'afternoon'
C:\Users\USER\AppData\Local\Temp\ipykernel_2580\1840100055.py:6: SettingWithCopyWarning: 
A value is trying to be set on a copy of a slice from a DataFrame

See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy
  bike_df['period_ofday'][(bike_df['start_hour'] >=18) & (bike_df['start_hour'] <=23)] = 'night'


#Testing the start hour and time of day columns created.
print(bike_df['start_hour'].value_counts())
print(bike_df['period_ofday'].value_counts())

17    21864
8     21056
18    16827
9     15903
16    14169
7     10614
19     9881
15     9174
12     8724
13     8551
10     8364
14     8152
11     7884
20     6482
21     4561
6      3485
22     2916
23     1646
0       925
5       896
1       548
2       381
4       235
3       174
Name: start_hour, dtype: int64
afternoon    70634
morning      70465
night        42313
Name: period_ofday, dtype: int64


#convert time period of day into ordered categorical data type.
ordinal_dict = {'period_ofday': ['morning', 'afternoon', 'night']}

for item in ordinal_dict:
    ordered_var = pd.api.types.CategoricalDtype(ordered = True, categories = ordinal_dict[item])
    bike_df[item] = bike_df[item].astype(ordered_var)


# creating the age variable/feature
bike_df['age']=bike_df['member_birth_year'].apply(lambda birth_year : 2019 - birth_year )


# Testing if age variable  has been added to the dataset.
print(bike_df.info())

<class 'pandas.core.frame.DataFrame'>
RangeIndex: 183412 entries, 0 to 183411
Data columns (total 19 columns):
 #   Column                   Non-Null Count   Dtype         
---  ------                   --------------   -----         
 0   duration_sec             183412 non-null  int64         
 1   start_time               183412 non-null  datetime64[ns]
 2   end_time                 183412 non-null  object        
 3   start_station_id         183412 non-null  object        
 4   start_station_name       183412 non-null  object        
 5   start_station_latitude   183412 non-null  float64       
 6   start_station_longitude  183412 non-null  float64       
 7   end_station_id           183412 non-null  object        
 8   end_station_name         183412 non-null  object        
 9   end_station_latitude     183412 non-null  float64       
 10  end_station_longitude    183412 non-null  float64       
 11  bike_id                  183412 non-null  object        
 12  user_type                183412 non-null  category      
 13  member_birth_year        183412 non-null  int64         
 14  member_gender            183412 non-null  category      
 15  bike_share_for_all_trip  183412 non-null  object        
 16  start_hour               183412 non-null  int64         
 17  period_ofday             183412 non-null  category      
 18  age                      183412 non-null  int64         
dtypes: category(3), datetime64[ns](1), float64(4), int64(4), object(7)
memory usage: 22.9+ MB
None


# plotting the distribution for the age of bike users.
plt.figure(figsize=[10, 8],dpi=100)
plt.hist(data = bike_df, x = 'age')
plt.xlabel('Member age')
plt.title('Distibution of Age for the Members')
plt.show()


# plotting the box plot to check the outliers clearly.
plt.figure(figsize=(8,6))
plt.boxplot(bike_df['age']);
plt.xlabel('Member Age (Years)')
plt.ylabel('Frequency')
plt.title('Distribution of Members Age');


# displaying the outliers in the age variable.
bike_df.query('age >= 100')


# dropping the outliers in the age variable.
bike_df.drop(bike_df.query('age >= 100').index, inplace= True)


# Checking if the outliers have been removed.
bike_df['age'].describe()

count    183340.000000
mean         34.016379
std           9.766728
min          18.000000
25%          27.000000
50%          31.000000
75%          38.000000
max          99.000000
Name: age, dtype: float64


# Using the log scale for the histogram of Member age.


# checking the descriptive statistics for age on a log scale.
np.log10(bike_df['age'].describe())

count    5.263257
mean     1.531688
std      0.989749
min      1.255273
25%      1.431364
50%      1.491362
75%      1.579784
max      1.995635
Name: age, dtype: float64


# Axis transformation for age distribution.
bins= 10 ** np.arange(1.26,2+0.025,0.025)
plt.figure(figsize=(10,8))
plt.hist(data=bike_df,x='age',bins=bins)
plt.xscale('log')
plt.title('Age Distribution on a log Scale');


# plotting the box plot to check if the outliers have been removed.
plt.figure(figsize=(8,6))
plt.boxplot(bike_df['age']);
plt.xlabel('Member Age (Year)')
plt.ylabel('Frequency')
plt.title('Distribution of Members Age');


# Plotting the 2 categorical variables user_type and member_gender to get an idea of the distribution of each.
fig, ax = plt.subplots(nrows=2, figsize=[10,10])
plot_color=sb.color_palette()[0]
sb.countplot(data=bike_df, x='user_type',color=plot_color,ax=ax[0])
sb.countplot(data=bike_df, x='member_gender',color=plot_color,ax=ax[1])
plt.show()


# we first begin by creating a new column called duration_min.
bike_df['duration_min']=bike_df['duration_sec']/60


# checking the summary statistics for trip duration in minutes.
bike_df['duration_min'].describe()

count    183340.000000
mean         12.101764
std          29.911955
min           1.016667
25%           5.416667
50%           8.566667
75%          13.266667
max        1424.066667
Name: duration_min, dtype: float64


# plotting the histogram for trip duration in minutes.
bin_size=300
bins=np.arange(0,bike_df['duration_min'].max()+bin_size, bin_size)
plt.figure(figsize=[10,8],dpi=100)
plt.hist(data=bike_df, x='duration_min',bins=bins)
plt.xlabel('duration (min)')
plt.title('Trip duration in Minutes', fontsize=15)
plt.show()


# plotting the histogram with an addition of the xlim.
plt.figure(figsize=[10,8],dpi=200)
plt.hist(data=bike_df, x='duration_min',bins=100)
plt.xlabel('duration (min)')
plt.xlim((0,100));
plt.title('Trip duration in Minutes', fontsize=15)
plt.show()


# plotting the barplot to check the most frequent period of the day when most trips are booked.
freq=bike_df['period_ofday'].value_counts()
order_period=freq.index
plt.figure(figsize=[10,10])
plot_color=sb.color_palette()[0]
sb.countplot(data=bike_df, x='period_ofday',color=plot_color,order=order_period)
plt.show()


# plotting the barplot for the period of day with percentages on top.
total_period=bike_df['period_ofday'].value_counts().sum()
plt.figure(figsize=[10,10],dpi=100)
sb.countplot(data=bike_df,y='period_ofday',color='lightgray',order=order_period);
for j in range(freq.shape[0]):
    count=freq[j]
    pct_string='{:0.1f}'.format(100*count/total_period)
    plt.text(count+1,j, pct_string, va="center")
    plt.xlabel('Frequency')
    plt.ylabel('Period of the day')
    plt.title('Period of the day with Most Trips')


#Plotting the pie chart for the top 5 popular start stations.
bike_df['start_station_name'].value_counts()[:5].plot(kind='pie',figsize=(10,10),autopct='%0.1F%%');
plt.title('Top Five Start Stations',fontsize=20);
pd.DataFrame(bike_df['start_station_name'].value_counts()[:5])


# plotting the barplot for the trip duration for each gender.
plt.figure(figsize=(10,8))
sb.barplot(data=bike_df,x='member_gender',y='duration_min')
plt.xlabel("Member Gender")
plt.ylabel('Trip duration (min)')
plt.title('Duration of trip for each gender in minutes');


# Checking the correlation between age and duration_min by plotting the heatmap.
numeric_vars=['age','duration_min']
plt.figure(figsize=(10,8))
sb.heatmap(bike_df[numeric_vars].corr(),annot=True,fmt='.2f',cmap='vlag_r',center=0)
plt.show()


# Scatter plot to Check the correlation between age and duration_min.
plt.figure(figsize=(10,6))
sb.regplot(data=bike_df,  x ='age', y ='duration_min');
plt.xlabel('Age (Years)')
plt.ylabel('Trip duration (min)');


# Checking the average trip duration time.
bike_df['duration_min'].describe()

count    183340.000000
mean         12.101764
std          29.911955
min           1.016667
25%           5.416667
50%           8.566667
75%          13.266667
max        1424.066667
Name: duration_min, dtype: float64


#plotting the relationship between age and user_type with the aid of a violin plot.
plt.figure(figsize = [16, 5],dpi=100)
base_color=sb.color_palette()[0]
plt.subplot(1,2,1)
ax1 = sb.violinplot(data=bike_df, y ='age', x='user_type', color=base_color)
plt.xticks(rotation = 15);

#plotting the relationship between age and user_type with the aid of a boxplot.
plt.subplot(1,2,2)
sb.boxplot(data=bike_df,  y = 'age', x='user_type', color=base_color)
plt.xticks(rotation = 15);
plt.ylim(ax1.get_ylim());


# plotting the relationship between the categorical varialbes  period_ofday, user_type and member_gender,
plt.figure(figsize=(10,10),dpi=100)

#Subplot 1: period_ofday vs user_type
plt.subplot(3,1,1)
sb.countplot(data=bike_df, x='period_ofday',hue='user_type',palette='Blues')


#Subplot 2: period_ofday vs member_gender
ax=plt.subplot(3,1,2)
sb.countplot(data=bike_df, x='period_ofday',hue='member_gender',palette='Blues')
ax.legend(ncol=2)

#Subplot 3: user_type vs member_gender
ax=plt.subplot(3,1,3)
sb.countplot(data=bike_df, x='user_type',hue='member_gender',palette='Reds')
ax.legend(loc=2, ncol=2)
plt.show()


def chart_plot(x):
    """This function groups a certain feature (x) by user_type and plots a pie chart representing the % of user types
       in relation to the given feature.
    """ 
    fea_stat=bike_df.groupby([x],as_index=False)["user_type"].count()
    chart_plot=px.pie(fea_stat,names=x,values='user_type',color_discrete_sequence=px.colors.sequential.RdBu,width=700,height=600 )
    return chart_plot


chart_plot('member_gender')


chart_plot('period_ofday')


# plotting the period of day trip duration for each user type using the clustered barplot.
plt.figure(figsize=[10,8],dpi=100)
plot=sb.barplot(data=bike_df, x = 'period_ofday', y='duration_min', hue='user_type',ci=None)
plot.set(xlabel="Period of day", ylabel='Trip duration (min)')
plt.title('Period of day duration usage');


# Plotting the relationship between member_gender, age and duration_min.
plt.figure(figsize=[10,10],dpi=200);
sb.scatterplot(data=bike_df ,x='age',y='duration_min',hue= 'member_gender', linewidth =0);


# plotting the correlation matrix for all the variables in the dataset.
plt.figure(figsize=(10,8))
sb.heatmap(bike_df.corr(),annot=True,fmt='.2f',cmap='vlag_r',center=0)
plt.show()


# Plotting the relationship between member_gender, age and user_type using a pointplot.
fig = plt.figure(figsize = [10,8],dpi=100)
ax = sb.pointplot(data = bike_df, x = 'member_gender', y = 'age', hue = 'user_type',
           palette = 'Blues', linestyles = '', dodge = True,errorbar="sd")
plt.title('Members\' age across gender and user types')
plt.xlabel('Member Gender')
plt.ylabel(' Age (Year)')
plt.show();

	duration_sec	start_time	end_time	start_station_id	start_station_name	start_station_latitude	start_station_longitude	end_station_id	end_station_name	end_station_latitude	end_station_longitude	bike_id	user_type	member_birth_year	member_gender	bike_share_for_all_trip
0	52185	2019-02-28 17:32:10.1450	2019-03-01 08:01:55.9750	21.0	Montgomery St BART Station (Market St at 2nd St)	37.789625	-122.400811	13.0	Commercial St at Montgomery St	37.794231	-122.402923	4902	Customer	1984.0	Male	No
1	42521	2019-02-28 18:53:21.7890	2019-03-01 06:42:03.0560	23.0	The Embarcadero at Steuart St	37.791464	-122.391034	81.0	Berry St at 4th St	37.775880	-122.393170	2535	Customer	NaN	NaN	No
2	61854	2019-02-28 12:13:13.2180	2019-03-01 05:24:08.1460	86.0	Market St at Dolores St	37.769305	-122.426826	3.0	Powell St BART Station (Market St at 4th St)	37.786375	-122.404904	5905	Customer	1972.0	Male	No
3	36490	2019-02-28 17:54:26.0100	2019-03-01 04:02:36.8420	375.0	Grove St at Masonic Ave	37.774836	-122.446546	70.0	Central Ave at Fell St	37.773311	-122.444293	6638	Subscriber	1989.0	Other	No
4	1585	2019-02-28 23:54:18.5490	2019-03-01 00:20:44.0740	7.0	Frank H Ogawa Plaza	37.804562	-122.271738	222.0	10th Ave at E 15th St	37.792714	-122.248780	4898	Subscriber	1974.0	Male	Yes

	duration_sec	start_station_id	start_station_latitude	start_station_longitude	end_station_id	end_station_latitude	end_station_longitude	bike_id	member_birth_year
count	183412.000000	183412.000000	183412.000000	183412.000000	183412.000000	183412.000000	183412.000000	183412.000000	183412.000000
mean	726.078435	138.503866	37.771223	-122.352664	136.174743	37.771427	-122.352250	4472.906375	1984.950347
std	1794.389780	111.750001	0.099581	0.117097	111.478306	0.099490	0.116673	1664.383394	9.908290
min	61.000000	3.000000	37.317298	-122.453704	3.000000	37.317298	-122.453704	11.000000	1878.000000
25%	325.000000	47.000000	37.770083	-122.412408	44.000000	37.770407	-122.411726	3777.000000	1981.000000
50%	514.000000	104.000000	37.780760	-122.398285	100.000000	37.781010	-122.398279	4958.000000	1988.000000
75%	796.000000	239.000000	37.797280	-122.286533	235.000000	37.797320	-122.288045	5502.000000	1992.000000
max	85444.000000	398.000000	37.880222	-121.874119	398.000000	37.880222	-121.874119	6645.000000	2001.000000

	duration_sec	start_time	end_time	start_station_id	start_station_name	start_station_latitude	start_station_longitude	end_station_id	end_station_name	end_station_latitude	end_station_longitude	bike_id	user_type	member_birth_year	member_gender	bike_share_for_all_trip	start_hour	period_ofday	age
1285	148	2019-02-28 19:29:17.627	2019-02-28 19:31:45.9670	158.0	Shattuck Ave at Telegraph Ave	37.833279	-122.263490	173.0	Shattuck Ave at 55th St	37.840364	-122.264488	5391	Subscriber	1900	Male	Yes	19	night	119
10827	1315	2019-02-27 19:21:34.436	2019-02-27 19:43:30.0080	343.0	Bryant St at 2nd St	37.783172	-122.393572	375.0	Grove St at Masonic Ave	37.774836	-122.446546	6249	Subscriber	1900	Male	No	19	night	119
16087	1131	2019-02-27 08:37:36.864	2019-02-27 08:56:28.0220	375.0	Grove St at Masonic Ave	37.774836	-122.446546	36.0	Folsom St at 3rd St	37.783830	-122.398870	4968	Subscriber	1900	Male	No	8	morning	119
19375	641	2019-02-26 17:03:19.855	2019-02-26 17:14:01.6190	9.0	Broadway at Battery St	37.798572	-122.400869	30.0	San Francisco Caltrain (Townsend St at 4th St)	37.776598	-122.395282	6164	Customer	1900	Male	No	17	afternoon	119
21424	1424	2019-02-26 08:58:02.904	2019-02-26 09:21:47.7490	375.0	Grove St at Masonic Ave	37.774836	-122.446546	343.0	Bryant St at 2nd St	37.783172	-122.393572	5344	Subscriber	1900	Male	No	8	morning	119
...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...
171996	1368	2019-02-03 17:33:54.607	2019-02-03 17:56:42.9490	37.0	2nd St at Folsom St	37.785000	-122.395936	375.0	Grove St at Masonic Ave	37.774836	-122.446546	4988	Subscriber	1900	Male	No	17	afternoon	119
173711	993	2019-02-03 09:45:30.464	2019-02-03 10:02:04.1690	375.0	Grove St at Masonic Ave	37.774836	-122.446546	36.0	Folsom St at 3rd St	37.783830	-122.398870	5445	Subscriber	1900	Male	No	9	morning	119
177708	1527	2019-02-01 19:09:28.387	2019-02-01 19:34:55.9630	343.0	Bryant St at 2nd St	37.783172	-122.393572	375.0	Grove St at Masonic Ave	37.774836	-122.446546	5286	Subscriber	1900	Male	No	19	night	119
177885	517	2019-02-01 18:38:40.471	2019-02-01 18:47:18.3920	25.0	Howard St at 2nd St	37.787522	-122.397405	30.0	San Francisco Caltrain (Townsend St at 4th St)	37.776598	-122.395282	2175	Subscriber	1902	Female	No	18	night	117
182830	428	2019-02-01 07:45:05.934	2019-02-01 07:52:14.9220	284.0	Yerba Buena Center for the Arts (Howard St at ...	37.784872	-122.400876	67.0	San Francisco Caltrain Station 2 (Townsend St...	37.776639	-122.395526	5031	Subscriber	1901	Male	No	7	morning	118

	start_station_name
Market St at 10th St	3904
San Francisco Caltrain Station 2 (Townsend St at 4th St)	3542
Berry St at 4th St	3051
Montgomery St BART Station (Market St at 2nd St)	2895
Powell St BART Station (Market St at 4th St)	2760

Part I - Data Exploration: Ford GoBike Trip data¶

by Ketty Muwowo¶

Table of Contents¶

Introduction¶

Questions¶

Univariate Exploration¶

Bivariate Exploration¶

Multivariate Exploration¶

Preliminary Wrangling¶

What is the structure of your dataset?¶

The Structure of the dataset¶

What is/are the main feature(s) of interest in your dataset?¶

What features in the dataset do you think will help support your investigation into your feature(s) of interest?¶

Univariate Exploration¶

What is the distribution for members' ages?¶

What is the distribution for member_gender and user_type features?¶

What is the distribution for the trip duration in minutes?¶

During what period of the day are more trips likely to be booked?¶

What are the top 5 popular start stations for the trips taken?¶

Discuss the distribution(s) of your variable(s) of interest. Were there any unusual points? Did you need to perform any transformations?¶

Of the features you investigated, were there any unusual distributions? Did you perform any operations on the data to tidy, adjust, or change the form of the data? If so, why did you do this?¶

Bivariate Exploration¶

For each gender, how long, in minutes, does the trip last?¶

Is there any correlation between Member age and duration of trip?¶

What is the relationship between age and user_type?¶

What is the relationship between the 3 categorical variables period_ofday, user_type and member_gender?¶

Talk about some of the relationships you observed in this part of the investigation. How did the feature(s) of interest vary with other features in the dataset?¶

Did you observe any interesting relationships between the other features (not the main feature(s) of interest)?¶

Multivariate Exploration¶

For each period of the day, what is the average trip duration in minutes for each user type?¶

What is the relationship between member_gender, age and duration_min?¶

How closely correlated are the different variables in the dataset?¶

What is the relationship between member_gender, age and user_type?¶

Talk about some of the relationships you observed in this part of the investigation. Were there features that strengthened each other in terms of looking at your feature(s) of interest?¶

Were there any interesting or surprising interactions between features?¶

Conclusions¶